Every agent run gets its own box, isolated by default
Firecracker microVMs for the code your agents write. Start one in a single call, pause and resume it, on one simple monthly plan.
Start building for freeCompute for agents, run by us
Sandboxes, workspaces, build machines and your own lab hardware behind one API. No servers to set up.
Sandscale compute, US East and EU. Sandboxes, workspaces and build hosts on our machines in N. Virginia and Frankfurt, ready with one API call.
Your lab, connected. Plug in your own Linux or macOS machines with real devices and claim them per run.
Firecracker microVMs for agent code. Run commands, move files, stream logs, snapshot, pause and resume.
A persistent cloud computer for your coding agent, with your repo, terminals and SSH. Keep working from any device.
Lease a clean build machine for a set time, sync your tree and run over SSH with a short-lived certificate. Wiped on release.
Connect your own Linux or macOS machines with security keys, TPMs, debug probes and boards, and claim them per run.
Why teams and developers run agents on Sandscale
Agents need a place to run code nobody has read
Running it on Sandscale
See inside
every agent run
Claude Code runs under your policy through its hooks: each tool call is allowed, blocked or sent to a person. Codex and Gemini CLI report every step over OpenTelemetry. Pause or stop any session from the dashboard.
See sandboxes →Policy
and audit
Decide which templates, sizes, run times and agents each project may use, and which calls need a person first. Every sandbox, workspace, lease and change lands in a hash-chained audit log you can export.
How we secure it →- Templates
- python-3.12, node-22
- Largest sandbox
- 4 vCPU
- Longest run
- 2 hours
- Network
- Off
- Per person
- 5 at once
- Agents
- Claude Code, Codex
- Ask first
- git push, gh pr create
- Block
- piped installs, rm -rf /
Start free. Scale when your agents do.
(Every plan runs on the same isolated microVMs.)
Sandboxes, workspaces and build hosts all draw from your plan's monthly hours. Pro gives one developer room to work; Team adds the controls a company needs; Enterprise adds your own cloud and your own keys.
Compare all features
| Free | Pro | Team | Enterprise | |
|---|---|---|---|---|
| Compute | ||||
| Members | 1 | 1 | 2 or more | Custom |
| Included vCPU-hours a month | 100 | 750 | 1,000 per member, pooled | Custom |
| Running at once | 2 | 20 | 100 | Custom |
| Largest box | Up to 2 vCPU | Up to 8 vCPU | Up to 16 vCPU | Up to 64 vCPU on request |
| Usage beyond your hours | No | Turn on or off | Turn on or off | Per agreement |
| Regions | US and Europe | US and Europe | US and Europe | US and Europe |
| Products | ||||
| Sandboxes | ✓ | ✓ | ✓ | ✓ |
| Pause and resume | ✓ | ✓ | ✓ | ✓ |
| Snapshots | No | ✓ | ✓ | ✓ |
| Workspaces | No | ✓ | ✓ | ✓ |
| Build hosts | No | Leases up to 4 h | Leases up to 12 h | ✓ |
| Lab hosts | No | No | ✓ | ✓ |
| Agent Cloud | No | ✓ | ✓ | ✓ |
| Object storage (US now, Europe coming soon) | No | 50 GB | 500 GB | Custom |
| Network and security | ||||
| Network | Off | Allowlist | Allowlist | Allowlist |
| Vault for secrets | No | ✓ | ✓ | ✓ |
| Audit log | Basic | Basic | With export | With export |
| Approvals and policies, projects | No | No | ✓ | ✓ |
| DLP on prompts and tool calls (Enterprise) | No | No | No | ✓ |
| Passkeys and multi-factor sign-in | ✓ | ✓ | ✓ | ✓ |
| Team and enterprise | ||||
| Organisations, invitations, roles, groups | No | No | ✓ | ✓ |
| SSO (SAML and OpenID Connect) | No | No | ✓ | ✓ |
| SCIM, verified domains, custom roles | No | No | No | ✓ |
| Your own encryption keys | No | No | No | ✓ |
| Custom sign-in domain and branding | No | No | No | ✓ |
| Dedicated capacity | No | No | No | ✓ |
| Bring your own cloud (AWS; Azure and Google Cloud coming soon) | No | No | No | ✓ |
| Support | ||||
| Support | Docs and community | Support terms in your agreement | ||
On paid plans you choose what happens when your included hours run out: turn usage beyond them on, or keep it off and your sandboxes and workspaces wait for next month. On Enterprise you can also run on your own cloud.
Need bigger machines? Enterprise can run boxes of up to 64 vCPU on request.
Everything a run needs
Start it, watch it, stop it. From your agent, your terminal or the dashboard.
Start, pause, snapshot and stop sandboxes from the API, the sandscale CLI or MCP. Every action lands in a tamper-evident audit log.
Sandboxes, workspaces, build hosts and lab hardware run on the same platform, managed from one dashboard and billed as one monthly plan.
Its own kernel per run, the network off until your allowlist opens it, secrets kept in Vault and never in prompts, and a kill switch for your organisation.
Connect over MCP from Claude Code, Codex or your own agent framework. Each agent gets its own box, and you see what each one is doing.
Give every agent
a box of its own
Start free with 100 vCPU-hours a month. Upgrade when your agents need more.